MCP App StoreMCP App Store
from drclaw167
Check potential interactions between two or more drugs by combining FDA interaction data, PubChem compound info, and ChEMBL target overlap analysis into a unifi
This skill orchestrates queries across FDA interaction datasets, PubChem compound lookups, and ChEMBL target information to identify and summarize potential drug-drug interactions. It provides a practical workflow for clinical-pharmacology-oriented agents to fetch interaction reports, resolve compound metadata, and compare molecular targets for overlap or conflict. The skill expects connector access to three MCP/SCP servers and demonstrates example code for streamable HTTP connections.
Use this skill when evaluating safety or mechanistic overlap between medications (e.g., warfarin + aspirin), preparing clinical decision support summaries, or automating literature and database checks that support pharmacovigilance tasks. It is intended for research/clinical-support agents with appropriate data access and API keys.
Best for agents that can open streamable HTTP connections and call external MCP/SCP servers (research assistants, clinical decision support agents, and data-integration bots).
This skill checks drug-drug interactions using three MCP servers (FDA, PubChem, ChEMBL) hosted on the SCP platform. The SKILL.md provides a 3-step workflow but it's vague — no detail on how to compare or synthesize results. The Python code example is auto-generated boilerplate that doesn't pass actual arguments to tool calls. Requires an SCP Hub API key from a Chinese-hosted service. No bundled scripts to test.
Part of the DrClaw clinical pharmacology agent framework. Auto-generated skill template with minimal hand-written content. The code example is clearly scaffold-generated and non-functional as-is. No security issues found — no hardcoded credentials, destructive commands, or exfiltration. The external API calls are to the declared tool servers, though all traffic goes to a third-party domain (intern-ai.org.cn).
Ip2Location IO Automation (Composio)
Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.
Smalltalk MCP
Connects an LLM (Claude/OpenAI/etc.) to a live Smalltalk (Squeak/Cuis) image over MCP for browsing, evaluating and modifying Smalltalk code.
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
ACP Checkout — MCP Binding
Guidance to expose ACP checkout REST operations as MCP tools so agents can perform commerce flows (create/update/complete/cancel checkout).
Skyvern — AI Browser Automation
Cloud-first AI browser automation platform and SDKs for extracting data, filling forms, downloading files, and running multi-step web workflows from agents or c
Forcemanager Automation (Rube MCP)
Automate Forcemanager tasks via Rube MCP (Composio); discovers tools, ensures active connections, and runs toolkit workflows safely.
Code Mode for MCP Servers
Add a sandboxed code mode tool to an MCP server so LLMs run small processing scripts against large API responses and only the script output enters the model con
DAUB UI
A drop-in CSS+JS component library with 70+ carefully designed components and 20 theme families for fast, consistent UI building.
